{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3YK4DPWL7M75D7QV5US6H6OBAZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ed4e6bae5a668238e391e286c25afdd647117eb83f7db931fc0b88770c004443","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-19T08:36:45Z","title_canon_sha256":"f06f3c51800c2baaee3be82614450538a9375f5479d0f343b2dd0d47cda5293c"},"schema_version":"1.0","source":{"id":"1909.09148","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.09148","created_at":"2026-07-05T00:20:55Z"},{"alias_kind":"arxiv_version","alias_value":"1909.09148v2","created_at":"2026-07-05T00:20:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.09148","created_at":"2026-07-05T00:20:55Z"},{"alias_kind":"pith_short_12","alias_value":"3YK4DPWL7M75","created_at":"2026-07-05T00:20:55Z"},{"alias_kind":"pith_short_16","alias_value":"3YK4DPWL7M75D7QV","created_at":"2026-07-05T00:20:55Z"},{"alias_kind":"pith_short_8","alias_value":"3YK4DPWL","created_at":"2026-07-05T00:20:55Z"}],"graph_snapshots":[{"event_id":"sha256:f104ec7c66fc553e60b38f2820fc943ca40e4539b61a1c69cd22324cbdb64da2","target":"graph","created_at":"2026-07-05T00:20:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.09148/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data augmentation has been widely applied as an effective methodology to improve generalization in particular when training deep neural networks. Recently, researchers proposed a few intensive data augmentation techniques, which indeed improved accuracy, yet we notice that these methods augment data have also caused a considerable gap between clean and augmented data. In this paper, we revisit this problem from an analytical perspective, for which we estimate the upper-bound of expected risk using two terms, namely, empirical risk and generalization error, respectively. We develop an understan","authors_text":"Lingxi Xie, Qi Tian, Xin Chen, Yanfeng Wang, Ya Zhang, Zhuoxun He","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-19T08:36:45Z","title":"Data Augmentation Revisited: Rethinking the Distribution Gap between Clean and Augmented Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.09148","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:74b98de8e5b43baea8aabf5a542e511b1d8ce0edd6dbbbb8afb5f06040cb122b","target":"record","created_at":"2026-07-05T00:20:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ed4e6bae5a668238e391e286c25afdd647117eb83f7db931fc0b88770c004443","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-19T08:36:45Z","title_canon_sha256":"f06f3c51800c2baaee3be82614450538a9375f5479d0f343b2dd0d47cda5293c"},"schema_version":"1.0","source":{"id":"1909.09148","kind":"arxiv","version":2}},"canonical_sha256":"de15c1becbfb3fd1fe15ed25e3f9c10658d03899657913ce84967ed17fdbb023","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de15c1becbfb3fd1fe15ed25e3f9c10658d03899657913ce84967ed17fdbb023","first_computed_at":"2026-07-05T00:20:55.538258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:20:55.538258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HXUOURko903w2opWqIN8EWJ2w3uc+N2LFxtaYjxGgNY40I5UFpuNAiOYssE8b9AO1+9YxMa+YXg5gLnIZFToAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:20:55.538781Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.09148","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74b98de8e5b43baea8aabf5a542e511b1d8ce0edd6dbbbb8afb5f06040cb122b","sha256:f104ec7c66fc553e60b38f2820fc943ca40e4539b61a1c69cd22324cbdb64da2"],"state_sha256":"9e89a09c66ead344efbdeae7639349b6f0fd8331bf82280f0f34e6c8034d4eaa"}